Aging and reverse-aging Traditional Chinese painting images based on Web-mining

Lieu Hen Chen, Meng Feng Tsai, Chien Hui Hsu, Yu Sheng Chen

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

Traditional Chinese painting has a long history more than thousands of year. No matter when these paintings are drawn, all suffer deterioration caused both by aging and external forces. Restoring damaged artworks involves very professional issues beyond the scope of computer science. However, retouching their images with aging/reverse-aging effects throws down a very interesting challenge to us. Unfortunately, it is very difficult to physically simulate the optical properties of aging pigments and surface material. In addition, the conventional image processing approaches fail to consider the above-mentioned factors, as well as historical trends in color selection and utilization. This paper proposes a knowledge-based and progressive refinement approach to simulate and remove the aging effects in the images of traditional Chinese paintings. Web mining is an important technique which supports this approach by a large number of the source images. A database of information related to degrees of color fade over time is constructed by collecting, categorizing, and analyzing the images of paintings from different eras. In addition, relationships among color distribution histograms, the different subjects being depicted, the year or dynasty the painting was created, and the properties of different pigments are also tracked. To separate the aging coloration influence of pigment from surface, the untouched areas, which are intentionally left blank as a common motif in traditional Chinese paintings, are utilized to provide a useful clue. The acquired data are then modified and feedbacked into our system to progressively refine the results. At the final rendering stage, several image processing techniques are applied to further enhance image quality. By using our prototype system, both aging and reverse-aging processes can be simulated. Initial study results show that this approach has great potential in simulating aging effects on images of traditional Chinese paintings.

Original languageEnglish
Pages (from-to)285-309
Number of pages25
JournalNew Generation Computing
Volume31
Issue number4
DOIs
StatePublished - Oct 2013

Keywords

  • Color analysis
  • Color mapping
  • Color simulation
  • Traditional Chinese paintings
  • Web-mining

Fingerprint

Dive into the research topics of 'Aging and reverse-aging Traditional Chinese painting images based on Web-mining'. Together they form a unique fingerprint.

Cite this